Computational prediction of manually gated rare cells in flow cytometry data

FCM marker importance for MRD assessment in T-cell acute lymphoblastic leukemia: An AIEOP-BFM-ALL-FLOW study group report

T-lineage acute lymphoblastic leukemia (T-ALL) accounts for about 15% of pediatric and about 25% of adult ALL cases. Minimal/measurable residual disease (MRD) assessed by flow cytometry (FCM) is an important prognostic indicator for risk stratification. In order to assess the MRD a limited number of antibodies directed against the most discriminative antigens must be selected. We propose a pipeline for evaluating the influence of different markers for cell population classification in FCM data. We use linear support vector machine, fitted to each sample individually to avoid issues with patient and laboratory variations. The best separating hyperplane direction as well as the influence of omitting specific markers is considered. Ninety-one bone marrow samples of 43 pediatric T-ALL patients from five reference laboratories were analyzed by FCM regarding marker importance for blast cell identification using combinations of eight different markers. For all laboratories, CD48 and CD99 were among the top three markers with strongest contribution to the optimal hyperplane, measured by median separating hyperplane coefficient size for all samples per center and time point (diagnosis, Day 15, Day 33). Based on the available limited set tested (CD3, CD4, CD5, CD7, CD8, CD45, CD48, CD99), our findings prove that CD48 and CD99 are useful markers for MRD monitoring in T-ALL. The proposed pipeline can be applied for evaluation of other marker combinations in the future.

A Chunking-for-Pooling Strategy for Cytometric Representation Learning for Automatic Hematologic Malignancy Classification

Differentiating types of hematologic malignancies is vital to determine therapeutic strategies for the newly diagnosed patients. Flow cytometry (FC) can be used as diagnostic indicator by measuring the multi-parameter fluorescent markers on thousands of antibody-bound cells, but the manual interpretation of large scale flow cytometry data has long been a time-consuming and complicated task for hematologists and laboratory professionals. Past studies have led to the development of representation learning algorithms to perform sample-level automatic classification. In this work, we propose a chunking-for-pooling strategy to include large-scale FC data into a supervised deep representation learning procedure for automatic hematologic malignancy classification. The use of discriminatively-trained representation learning strategy and the fixed-size chunking and pooling design are key components of this framework. It improves the discriminative power of the FC sample-level embedding and simultaneously addresses the robustness issue due to an inevitable use of down-sampling in conventional distribution based approaches for deriving FC representation. We evaluated our framework on two datasets. Our framework outperformed other baseline methods and achieved 92.3% unweighted average recall (UAR) for four-class recognition on the UPMC dataset and 85.0% UAR for five-class recognition on the hema.to dataset. We further compared the robustness of our proposed framework with that of the traditional downsampling approach. Analysis of the effects of the chunk size and the error cases revealed further insights about different hematologic malignancy characteristics in the FC data.

Dual delivery of IL-10 and AT-RvD1 from PEG hydrogels polarize immune cells towards pro-regenerative phenotypes

Inflammation after traumatic injury or surgical intervention is both a protective tissue response leading to regeneration and a potential cause of wound complications. One potentially successful strategy to harness to pro-regenerative roles of host inflammation is the localized delivery of bioactive materials to induce immune suppressive cellular responses by cells responding to injury. In this study, we designed a fully synthetic poly (ethylene) glycol (PEG)-based hydrogel to release the specialized pro-resolving lipid mediator aspirin-triggered resolvin-D1 (AT-RvD1) and recombinant human interleukin 10 (IL-10). We utilized a unique side-by-side internally controlled implant design wherein bioactive hydrogels were implanted adjacent to control hydrogels devoid of immune modulatory factors in the dorsal skinfold window chamber. We also explored single-immune cell data with unsupervised approaches such as SPADE. First, we show that RGD-presenting hydrogel delivery results in enhanced immune cell recruitment to the site of injury. We then use intra-vital imaging to assess cellular recruitment and microvascular remodeling to show an increase in the caliber and density of local microvessels. Finally, we show that the recruitment and re-education of mononuclear phagocytes by combined delivery IL-10 and AT-RvD1 localizes immune suppressive subsets to the hydrogel, including CD206+ macrophages (M2a/c) and IL-10 expressing dendritic cells in the context of chronic inflammation following surgical tissue disruption. These data demonstrate the potential of combined delivery on the recruitment of regenerative cell subsets involved in wound healing complications.

Application of machine learning in the management of acute myeloid leukemia: current practice and future prospects

Machine learning (ML) is rapidly emerging in several fields of cancer research. ML algorithms can deal with vast amounts of medical data and provide a better understanding of malignant disease. Its ability to process information from different diagnostic modalities and functions to predict prognosis and suggest therapeutic strategies indicates that ML is a promising tool for the future management of hematologic malignancies; acute myeloid leukemia (AML) is a model disease of various recent studies. An integration of these ML techniques into various applications in AML management can assure fast and accurate diagnosis as well as precise risk stratification and optimal therapy. Nevertheless, these techniques come with various pitfalls and need a strict regulatory framework to ensure safe use of ML. This comprehensive review highlights and discusses recent advances in ML techniques in the management of AML as a model disease of hematologic neoplasms, enabling researchers and clinicians alike to critically evaluate this upcoming, potentially practice-changing technology.

From big flow cytometry datasets to smart diagnostic strategies: The EuroFlow approach

The rise in the analytical speed of mutiparameter flow cytometers made possible by the introduction of digital instruments, has brought up the possibility to manage progressively higher number of parameters simultaneously on significantly greater numbers of individual cells. This has led to an exponential increase in the complexity and volume of flow cytometry data generated about cells present in individual samples evaluated in a single measurement. This increase demands for new developments in flow cytometry data analysis, graphical representation, and visualization and interpretation tools to address the new big data challenges, i.e. processing data files of ≥10-25 parameters per cell in samples with >5-10 million cells (= up to 250 million data points per cell sample) obtained in a few minutes. Here, we present a comprehensive review of some of the tools developed by the EuroFlow consortium for processing flow cytometric big data files in diagnostic laboratories, particularly focused on automated EuroFlow approaches for: i) identification of all cell populations coexisting in a sample (automated gating); ii) smart classification of aberrant cell populations in routine diagnostics; iii) automated reporting; together with iv) new tools developed to visualize n-dimensional data in 2-dimensional plots to support expert-guided automated data analysis. The concept of using reference data bases implemented into software programs, in combination with multivariate statistical analysis pioneered by EuroFlow, provides an innovative, highly efficient and fast approach for diagnostic screening, classification and monitoring of patients with distinct hematological and immune disorders, as well as other diseases.

Statistical performance of image cytometry for DNA, lipids, cytokeratin, & CD45 in a model system for circulation tumor cell detection

Detection of circulating tumor cells (CTCs) in a blood sample is limited by the sensitivity and specificity of the biomarker panel used to identify CTCs over other blood cells. In this work, we present Bayesian theory that shows how test sensitivity and specificity set the rarity of cell that a test can detect. We perform our calculation of sensitivity and specificity on our image cytometry biomarker panel by testing on pure disease positive (D⁺ ) populations (MCF7 cells) and pure disease negative populations (D^- ) (leukocytes). In this system, we performed multi-channel confocal fluorescence microscopy to image biomarkers of DNA, lipids, CD45, and Cytokeratin. Using custom software, we segmented our confocal images into regions of interest consisting of individual cells and computed the image metrics of total signal, second spatial moment, spatial frequency second moment, and the product of the spatial-spatial frequency moments. We present our analysis of these 16 features. The best performing of the 16 features produced an average separation of three standard deviations between D⁺ and D^- and an average detectable rarity of ∼1 in 200. We performed multivariable regression and feature selection to combine multiple features for increased performance and showed an average separation of seven standard deviations between the D⁺ and D^- populations making our average detectable rarity of ∼1 in 480. Histograms and receiver operating characteristics (ROC) curves for these features and regressions are presented. We conclude that simple regression analysis holds promise to further improve the separation of rare cells in cytometry applications. © 2017 International Society for Advancement of Cytometry.

Toward deterministic and semiautomated SPADE analysis

SPADE stands for spanning-tree progression analysis for density-normalized events. It combines downsampling, clustering and a minimum-spanning tree to provide an intuitive visualization of high-dimensional single-cell data, which assists with the interpretation of the cellular heterogeneity underlying the data. SPADE has been widely used for analysis of high-content flow cytometry data and CyTOF data. The downsampling and clustering components of SPADE are both stochastic, which lead to stochasticity in the tree visualization it generates. Running SPADE twice on the same data may generate two different tree structures. Although they typically lead to the same biological interpretation of subpopulations present in the data, robustness of the algorithm can be improved. Another avenue of improvement is the interpretation of the SPADE tree, which involves visual inspection of multiple colored versions of the tree based on expression of measured markers. This is essentially manual gating on the SPADE tree and can benefit from automated algorithms. This article presents improvements of SPADE in both aspects above, leading to a deterministic SPADE algorithm and a software implementation for semiautomated interpretation. © 2017 International Society for Advancement of Cytometry.

Single and multi-subject clustering of flow cytometry data for cell-type identification and anomaly detection

BACKGROUND

Measurement of various markers of single cells using flow cytometry has several biological applications. These applications include improving our understanding of behavior of cellular systems, identifying rare cell populations and personalized medication. A common critical issue in the existing methods is identification of the number of cellular populations which heavily affects the accuracy of results. Furthermore, anomaly detection is crucial in flow cytometry experiments. In this work, we propose a two-stage clustering technique for cell type identification in single subject flow cytometry data and extend it for anomaly detection among multiple subjects.

RESULTS

Our experimentation on 42 flow cytometry datasets indicates high performance and accurate clustering (F-measure > 91 %) in identifying main cellular populations. Furthermore, our anomaly detection technique evaluated on Acute Myeloid Leukemia dataset results in only <2 % false positives.

Multi-parametric cytometry from a complex cellular sample: Improvements and limits of manual versus computational-based interactive analyses

The wide possibilities opened by the developments of multi-parametric cytometry are limited by the inadequacy of the classical methods of analysis to the multi-dimensional characteristics of the data. While new computational tools seemed ideally adapted and were applied successfully, their adoption is still low among the flow cytometrists. In the purpose to integrate unsupervised computational tools for the management of multi-stained samples, we investigated their advantages and limits by comparison to manual gating on a typical sample analyzed in immunomonitoring routine. A single tube of PBMC, containing 11 populations characterized by different sizes and stained with 9 fluorescent markers, was used. We investigated the impact of the strategy choice on manual gating variability, an undocumented pitfall of the analysis process, and we identified rules to optimize it. While assessing automatic gating as an alternate, we introduced the Multi-Experiment Viewer software (MeV) and validated it for merging clusters and annotating interactively populations. This procedure allowed the finding of both targeted and unexpected populations. However, the careful examination of computed clusters in standard dot plots revealed some heterogeneity, often below 10%, that was overcome by increasing the number of clusters to be computed. MeV facilitated the identification of populations by displaying both the MFI and the marker signature of the dataset simultaneously. The procedure described here appears fully adapted to manage homogeneously high number of multi-stained samples and allows improving multi-parametric analyses in a way close to the classic approach. © 2016 International Society for Advancement of Cytometry.